{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T07:10:59Z","timestamp":1774595459346,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1109\/ieeeconf67917.2025.11443839","type":"proceedings-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:47:37Z","timestamp":1774554457000},"page":"280-284","source":"Crossref","is-referenced-by-count":0,"title":["History-Augmented Vision-Language Models for Frontier-Based Zero-Shot Object Navigation"],"prefix":"10.1109","author":[{"given":"Mobin","family":"Habibpour","sequence":"first","affiliation":[{"name":"Clemson University,Holcombe Department of Electrical and Computer Engineering,Clemson,SC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatemeh","family":"Afghah","sequence":"additional","affiliation":[{"name":"Clemson University,Holcombe Department of Electrical and Computer Engineering,Clemson,SC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3569122"},{"key":"ref2","article-title":"Vision-and-language navigation today and tomorrow: A survey in the era of foundation models","author":"Zhang","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49997.2022.9926452"},{"key":"ref4","article-title":"Clip-nav: Using clip for zero-shot vision-and-language navigation","author":"Dorbala","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3378010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref7","article-title":"Gamap: Zero-shot object goal navigation with multi-scale geometric-affordance guidance","author":"Yuan","year":"2024"},{"key":"ref8","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref9","article-title":"Clip on wheels: Zero-shot object navigation as object localization and exploration","author":"Gadre","year":"2022"},{"key":"ref10","article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","author":"Majumdar","year":"2023"},{"key":"ref11","article-title":"Habitat challenge 2023","author":"Yadav","year":"2023"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.02484","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2024"},{"key":"ref13","article-title":"Pali: A jointly-scaled multilingual language-image model","author":"Chen","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00390"},{"key":"ref15","article-title":"Frontier based exploration for autonomous robot","author":"Topiwala","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0561"},{"key":"ref17","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref18","article-title":"Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2022"},{"key":"ref19","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2015"},{"key":"ref20","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2024"},{"key":"ref21","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref23","article-title":"Imaginenav: Prompting vision-language models as embodied navigator through scene imagination","author":"Zhao","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610499"}],"event":{"name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2025,10,26]]},"end":{"date-parts":[[2025,10,29]]}},"container-title":["2025 59th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443114\/11443296\/11443839.pdf?arnumber=11443839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:38:09Z","timestamp":1774589889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf67917.2025.11443839","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}